List your company

Skill-based Task Execution on Skills-Bench 27-task headline sample

0.705Mean Task RewardAIP-compiled skills
0.594760.623380.6520.68062Jun 3, 2026

Evaluation results

MethodLinks
AIP-compiled skillsSolver=Claude Sonnet, Trials per task=52026.060.70567.451025.6121320.011
Human-curated skillsSolver=Claude Sonnet, Trials per task=52026.060.59953.358527.7————